mlsanityData to 14 Oct 2026

Neural Belief Propagation for Scene Graph Generation

arXiv 2112.05727 ↗First posted 10 Dec 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Scene graph generation aims to interpret an input image by explicitly modelling the potential objects and their relationships, which is predominantly solved by the message passing neural network models in previous methods. Currently, such approximation models generally assume the output variables are totally independent and thus ignore the informative structural higher-order interactions. This could lead to the inconsistent interpretations for an input image. In this paper, we propose a novel neural belief propagation method to generate the resulting scene graph. It employs a structural Bethe approximation rather than the mean field approximation to infer the associated marginals. To find a better bias-variance trade-off, the proposed model not only incorporates pairwise interactions but also higher order interactions into the associated scoring function. It achieves the state-of-the-art performance on various popular scene graph generation benchmarks.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 41 of its 56 references that are in the map. First posted on arXiv 10 Dec 2021.

Builds on

41 of 56 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  4. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  5. 2017Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answeringcited by 1,312
  6. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  7. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  8. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  9. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  10. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 605
  11. 2016Self-critical Sequence Training for Image Captioningcited by 547
  12. 2017Scene Graph Generation by Iterative Message Passingcited by 462
29 more
  1. 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 414
  2. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  3. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  4. 2020Unbiased Scene Graph Generation from Biased Trainingcited by 356
  5. 2018Graph R-CNN for Scene Graph Generationcited by 298
  6. 2016Image Captioning with Semantic Attentioncited by 260
  7. 2018Learning to Compose Dynamic Tree Structures for Visual Contextscited by 259
  8. 2018Auto-Encoding Scene Graphs for Image Captioningcited by 255
  9. 2017Advances in Variational Inferencecited by 236
  10. 2015Conditional Random Fields as Recurrent Neural Networkscited by 214
  11. 2020GPS-Net: Graph Property Sensing Network for Scene Graph Generationcited by 166
  12. 2019Knowledge-Embedded Routing Network for Scene Graph Generationcited by 164
  13. 2017Scene Graph Generation from Objects, Phrases and Region Captionscited by 154
  14. 2021Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generationcited by 137
  15. 2016Graph-Structured Representations for Visual Question Answeringcited by 123
  16. 2015Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networkscited by 115
  17. 2018Explainable and Explicit Visual Reasoning over Scene Graphscited by 103
  18. 2019Graphical Contrastive Losses for Scene Graph Parsingcited by 100
  19. 2017Detecting Visual Relationships with Deep Relational Networkscited by 97
  20. 2018Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generationcited by 78
  21. 2013Loopy Belief Propagation for Approximate Inference: An Empirical Studycited by 76
  22. 2018Attentive Relational Networks for Mapping Images to Scene Graphscited by 73
  23. 2020Neural Enhanced Belief Propagation on Factor Graphscited by 57
  24. 2020Learning to Segment the Tailcited by 54
  25. 2018Counterfactual Critic Multi-Agent Training for Scene Graph Generationcited by 53
  26. 2021From General to Specific: Informative Scene Graph Generation via Balance Adjustmentcited by 51
  27. 2018LinkNet: Relational Embedding for Scene Graphcited by 45
  28. 2020Belief Propagation Neural Networkscited by 33
  29. 2019Visual Semantic Information Pursuit: A Surveycited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 2; 2025: 0; 2026: 2.

6 papers.

  1. 2023Unbiased Scene Graph Generation via Two-stage Causal Modelingcited by 21
  2. 2022Dual-branch Hybrid Learning Network for Unbiased Scene Graph Generationcited by 10
  3. 2024SGTR+: End-to-end Scene Graph Generation with Transformercited by 1
  4. 2026In-Context Source and Channel Codingcited by 1
  5. 2026StreamEMS: Streaming Video Understanding with Self-Evolving Memory Scheme for Vision-Language Modelscited by 1
  6. 2024Unbiased Scene Graph Generation by Type-Aware Message Passing on Heterogeneous and Dual Graphscited by 0